DeepAI
Log In Sign Up

On-the-fly construction of surrogate constitutive models for concurrent multiscale mechanical analysis through probabilistic machine learning

07/11/2020
by   I. B. C. M. Rocha, et al.
0

Concurrent multiscale finite element analysis (FE2) is a powerful approach for high-fidelity modeling of materials for which a suitable macroscopic constitutive model is not available. However, the extreme computational effort associated with computing a nested micromodel at every macroscopic integration point makes FE2 prohibitive for most practical applications. Constructing surrogate models able to efficiently compute the microscopic constitutive response is therefore a promising approach in enabling concurrent multiscale modeling. This work presents a reduction framework for adaptively constructing surrogate models based on statistical learning. The nested micromodels are replaced by a machine learning surrogate model based on Gaussian Processes (GP). The need for offline data collection is bypassed by training the GP models online based on data coming from a small set of fully-solved anchor micromodels that undergo the same strain history as their associated macro integration points. The Bayesian formalism inherent to GP models provides a natural tool for uncertainty estimation through which new observations or inclusion of new anchors are triggered. The surrogate constitutive manifold is constructed with as few micromechanical evaluations as possible by enhancing the GP models with gradient information and the solution scheme is made robust through a greedy data selection approach embedded within the conventional finite element solution loop for nonlinear analysis. The sensitivity to model parameters is studied with a tapered bar example with plasticity, while the applicability of the model to more complex cases is demonstrated with the elastoplastic analysis of a plate with multiple cutouts and a crack growth example for mixed-mode bending. Significant efficiency gains are obtained without resorting to offline training.

READ FULL TEXT

page 2

page 22

07/12/2020

A computationally tractable framework for nonlinear dynamic multiscale modeling of membrane fabric

A general-purpose computational homogenization framework is proposed for...
09/29/2021

An FE-DMN method for the multiscale analysis of thermomechanical composites

We extend the FE-DMN method to fully coupled thermomechanical two-scale ...
12/19/2019

Assembly of multiscale linear PDE operators

In numerous applications the mathematical model consists of different pr...
03/15/2021

An FE-DMN method for the multiscale analysis of fiber reinforced plastic components

In this work, we propose a fully coupled multiscale strategy for compone...